dify/api/tasks/add_document_to_index_task.py

83 lines
2.7 KiB
Python
Raw Normal View History

2023-05-15 08:51:32 +08:00
import datetime
import logging
import time
import click
from celery import shared_task
from werkzeug.exceptions import NotFound
from core.rag.index_processor.index_processor_factory import IndexProcessorFactory
from core.rag.models.document import Document
2023-05-15 08:51:32 +08:00
from extensions.ext_database import db
from extensions.ext_redis import redis_client
from models.dataset import Document as DatasetDocument
from models.dataset import DocumentSegment
2023-05-15 08:51:32 +08:00
@shared_task(queue="dataset")
def add_document_to_index_task(dataset_document_id: str):
2023-05-15 08:51:32 +08:00
"""
Async Add document to index
:param document_id:
Usage: add_document_to_index.delay(document_id)
"""
logging.info(click.style("Start add document to index: {}".format(dataset_document_id), fg="green"))
2023-05-15 08:51:32 +08:00
start_at = time.perf_counter()
dataset_document = db.session.query(DatasetDocument).filter(DatasetDocument.id == dataset_document_id).first()
if not dataset_document:
raise NotFound("Document not found")
2023-05-15 08:51:32 +08:00
if dataset_document.indexing_status != "completed":
2023-05-15 08:51:32 +08:00
return
indexing_cache_key = "document_{}_indexing".format(dataset_document.id)
2023-05-15 08:51:32 +08:00
try:
segments = (
db.session.query(DocumentSegment)
.filter(DocumentSegment.document_id == dataset_document.id, DocumentSegment.enabled == True)
.order_by(DocumentSegment.position.asc())
.all()
)
2023-05-15 08:51:32 +08:00
documents = []
2023-05-15 08:51:32 +08:00
for segment in segments:
document = Document(
page_content=segment.content,
metadata={
"doc_id": segment.index_node_id,
"doc_hash": segment.index_node_hash,
"document_id": segment.document_id,
"dataset_id": segment.dataset_id,
},
2023-05-15 08:51:32 +08:00
)
documents.append(document)
2023-05-15 08:51:32 +08:00
dataset = dataset_document.dataset
2023-05-15 08:51:32 +08:00
if not dataset:
raise Exception("Document has no dataset")
2023-05-15 08:51:32 +08:00
index_type = dataset.doc_form
index_processor = IndexProcessorFactory(index_type).init_index_processor()
index_processor.load(dataset, documents)
2023-05-15 08:51:32 +08:00
end_at = time.perf_counter()
logging.info(
click.style(
"Document added to index: {} latency: {}".format(dataset_document.id, end_at - start_at), fg="green"
)
)
2023-05-15 08:51:32 +08:00
except Exception as e:
logging.exception("add document to index failed")
dataset_document.enabled = False
dataset_document.disabled_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
dataset_document.status = "error"
dataset_document.error = str(e)
2023-05-15 08:51:32 +08:00
db.session.commit()
finally:
redis_client.delete(indexing_cache_key)